Investigating risk assessment in post-pandemic household cryptocurrency investments: an explainable machine learning approach

This study provides an applicable methodological approach applying artificial intelligence (AI)-based supervised machine learning (ML) algorithms in risk assessment of post-pandemic household cryptocurrency investments and identifies the best performed ML algorithm most important determinants. The empirical findings from analyzing 13 determinants 1,000 dataset collected major communities online suggest that logistic regression (LR) outperforms remaining six by using performance metrics, lift chart, ROC chart. Moreover, to make results explainable tackle “black box” issue, top five are discovered, which interaction between investment amount duration, amount, perception traditional investments, literacy, volatility. present contributes literature on assessment, especially era body knowledge algorithms.